Robust decomposable Markov decision processes motivated by allocating school budgets.
Nedialko B. DimitrovStanko DimitrovStefanka ChukovaPublished in: Eur. J. Oper. Res. (2014)
Keyphrases
- markov decision processes
- finite state
- state space
- optimal policy
- transition matrices
- planning under uncertainty
- reinforcement learning algorithms
- policy iteration
- average cost
- reinforcement learning
- factored mdps
- dynamic programming
- decision theoretic planning
- average reward
- action space
- reachability analysis
- infinite horizon
- semi markov decision processes
- risk sensitive
- decision processes
- model based reinforcement learning
- action sets
- markov decision process
- finite horizon
- machine learning
- partially observable
- reward function
- stochastic shortest path
- decision diagrams
- optimal control
- decision problems
- heuristic search
- graphical models
- search algorithm
- interval estimation